Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1916 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1495. Min Act: -0.0003

Data Index: 1476373 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1508. Min Act: -0.0003

Data Index: 771642 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1520. Min Act: -0.0003

Data Index: 1630173 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1517. Min Act: -0.0003

Data Index: 1445957 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1446. Min Act: -0.0003

Data Index: 1541927 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1421. Min Act: -0.0003

Data Index: 1639032 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1420. Min Act: -0.0003

Data Index: 1399699 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1292. Min Act: -0.0003

Data Index: 1410713 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1647387 (Python Code)

Max Activating Token Index: 676

Text #9

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1304. Min Act: -0.0003

Data Index: 1460452 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1332. Min Act: -0.0004

Data Index: 1365565 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1259. Min Act: -0.0003

Data Index: 1589421 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1269. Min Act: -0.0003

Data Index: 1474965 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1244. Min Act: -0.0003

Data Index: 1623754 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1259. Min Act: -0.0003

Data Index: 1562827 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1231. Min Act: -0.0003

Data Index: 835796 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1220. Min Act: -0.0004

Data Index: 1588993 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1250. Min Act: -0.0003

Data Index: 549730 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1171. Min Act: -0.0003

Data Index: 1403662 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1240. Min Act: -0.0003

Data Index: 1481846 (Python Code)

Max Activating Token Index: 160